mcpField
M
meta-decision-analysis

meta-decision-analysis

github.com/asgard-ai-platformProductivity24350 installsUpdated 21w ago
Repository

About meta-decision-analysis

A decision-analysis skill for people comparing options under multiple criteria or uncertainty. It offers weighted scoring, decision trees and stakeholder-based analysis, with guidance on checking sensitivity and risk.

Key features

  1. 01Weighted decision matrices
  2. 02Decision trees for uncertainty
  3. 03Multi-criteria stakeholder analysis
  4. 04Sensitivity checks
  5. 05Risk and scoring guidance

Use cases

  1. 01Comparing options against weighted criteria
  2. 02Evaluating sequential choices with uncertain outcomes
  3. 03Identifying stakeholder agreement and trade-offs

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/asgard-ai-platform/skills --skill meta-decision-analysis

After installing, type/meta-decision-analysisin Claude Code to confirm it loaded.

Bundled filesexamples/sample_scenario.mdreferences/decision-tools.md

Details

From the project README

Decision Analysis

Framework

IRON LAW: Make Criteria and Weights Explicit BEFORE Evaluating Options

Choosing criteria after seeing the options lets bias sneak in — you
unconsciously weight criteria that favor your preferred option.
Define criteria, assign weights, THEN score options.
Decision Matrix (Weighted Scoring)
  1. List alternatives (3-6 options including "do nothing")
  2. Define criteria (4-8 factors that matter)
  3. Weight criteria (must sum to 100%)
  4. Score each option per criterion (1-5 or 1-10)
  5. Calculate weighted total = Σ(score × weight)
  6. Sensitivity check: Does the winner change if you adjust the top-weighted criterion?
Decision Tree (Sequential Decisions Under Uncertainty)

For decisions with uncertainty and sequential steps:

  1. Map decision nodes (squares) and chance nodes (circles)
  2. Assign probabilities to chance outcomes (must sum to 1.0)
  3. Assign payoffs to terminal nodes
  4. Calculate Expected Value = Σ(probability × payoff)
  5. Choose the branch with highest EV (or best risk-adjusted outcome)
Multi-Criteria Decision Analysis (MCDA)

For complex decisions with competing stakeholder priorities:

  1. Each stakeholder defines their criteria and weights independently
  2. Aggregate into a combined weighted matrix
  3. Identify where stakeholders agree (easy decisions) and disagree (requires negotiation)

Output Format

# Decision Analysis: {Decision}

## Alternatives
1. {Option A}
2. {Option B}
3. {Option C}

## Decision Matrix
| Criterion | Weight | Option A | Option B | Option C |
|-----------|--------|----------|----------|----------|
| {criterion 1} | {X%} | {1-5} | {1-5} | {1-5} |
| **Weighted Total** | 100% | **{total}** | **{total}** | **{total}** |

## Sensitivity Analysis
- If {criterion} weight changes from X% to Y%, winner changes from {A} to {B}

## Recommendation
{Winner with rationale and key trade-offs acknowledged}

Gotchas

  • "Do nothing" is always an option: Include it as a baseline. Sometimes the best decision is to wait.
  • Scores are subjective: A score of "4" from one person ≠ "4" from another. Calibrate by defining what each score means before scoring.
  • Expected value ignores risk preference: EV of $50 (certain) vs EV of $50 (50% chance of $0, 50% chance of $100) are equal by EV but feel very different. For high-stakes decisions, use risk-adjusted metrics.
  • Analysis paralysis: Decision analysis should accelerate decisions, not delay them. Set a time limit for the analysis.

References

  • For decision tree software tools, see references/decision-tools.md

Comments

Markdown supported